Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network

Shahabodin Afrasiabi; Sarah Allahmoradi; Xiaodong Liang; Mousa Afrasiabi; Jamshid Aghaei; C. Y. Chung

doi:10.1109/ETFG55873.2023.10407830

Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network

Shahabodin Afrasiabi
, Sarah Allahmoradi
, Xiaodong Liang
, Mousa Afrasiabi
, Jamshid Aghaei
, C. Y. Chung

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

1 Citation (Scopus)

Abstract

This paper introduces an unsupervised deep Bayesian network, built upon normalizing flow and deep Bayesian network principles, to precisely evaluate the transient security condition of a power system. The proposed approach can capture locational and temporal features using an imbalanced dataset, is noise-model-free, and can handle unlabeled data. It can learn interdependencies between different signals and understand high-dimensional signals in power systems. To validate its effectiveness, the proposed method is studied using the New England power system and shows accuracy and reliability in comparison with state-of-the-art deep networks (convolutional neural network (CNN) and long short-term memory (LSTM)) and shallow networks (support vector machine (SVM) and artificial neural network (ANN)).

Original language	English
Title of host publication	2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665471640
DOIs	https://doi.org/10.1109/ETFG55873.2023.10407830
Publication status	Published - Dec 2023
Event	2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023 - Wollongong, Australia Duration: 3 Dec 2023 → 6 Dec 2023

Publication series

Name	2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

Conference

Conference	2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023
Country/Territory	Australia
City	Wollongong
Period	3/12/23 → 6/12/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Bayesian network
imbalanced dataset
noise-model free
normalizing flow
transient security assessment
unsupervised deep learning

ASJC Scopus subject areas

Artificial Intelligence
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Control and Optimization
Safety, Risk, Reliability and Quality

More information

10.1109/ETFG55873.2023.10407830

Cite this

Afrasiabi, S., Allahmoradi, S., Liang, X., Afrasiabi, M., Aghaei, J., & Chung, C. Y. (2023). Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network. In 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023 (2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ETFG55873.2023.10407830

Afrasiabi, Shahabodin ; Allahmoradi, Sarah ; Liang, Xiaodong et al. / Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network. 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023).

@inproceedings{b5de671f00844940a35f103c24f72cfe,

title = "Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network",

abstract = "This paper introduces an unsupervised deep Bayesian network, built upon normalizing flow and deep Bayesian network principles, to precisely evaluate the transient security condition of a power system. The proposed approach can capture locational and temporal features using an imbalanced dataset, is noise-model-free, and can handle unlabeled data. It can learn interdependencies between different signals and understand high-dimensional signals in power systems. To validate its effectiveness, the proposed method is studied using the New England power system and shows accuracy and reliability in comparison with state-of-the-art deep networks (convolutional neural network (CNN) and long short-term memory (LSTM)) and shallow networks (support vector machine (SVM) and artificial neural network (ANN)).",

keywords = "Bayesian network, imbalanced dataset, noise-model free, normalizing flow, transient security assessment, unsupervised deep learning",

author = "Shahabodin Afrasiabi and Sarah Allahmoradi and Xiaodong Liang and Mousa Afrasiabi and Jamshid Aghaei and Chung, \{C. Y.\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023 ; Conference date: 03-12-2023 Through 06-12-2023",

year = "2023",

month = dec,

doi = "10.1109/ETFG55873.2023.10407830",

language = "English",

series = "2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023",

}

Afrasiabi, S, Allahmoradi, S, Liang, X, Afrasiabi, M, Aghaei, J & Chung, CY 2023, Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network. in 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023. 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023, Wollongong, Australia, 3/12/23. https://doi.org/10.1109/ETFG55873.2023.10407830

Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network. / Afrasiabi, Shahabodin; Allahmoradi, Sarah; Liang, Xiaodong et al.
2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network

AU - Afrasiabi, Shahabodin

AU - Allahmoradi, Sarah

AU - Liang, Xiaodong

AU - Afrasiabi, Mousa

AU - Aghaei, Jamshid

AU - Chung, C. Y.

PY - 2023/12

Y1 - 2023/12

N2 - This paper introduces an unsupervised deep Bayesian network, built upon normalizing flow and deep Bayesian network principles, to precisely evaluate the transient security condition of a power system. The proposed approach can capture locational and temporal features using an imbalanced dataset, is noise-model-free, and can handle unlabeled data. It can learn interdependencies between different signals and understand high-dimensional signals in power systems. To validate its effectiveness, the proposed method is studied using the New England power system and shows accuracy and reliability in comparison with state-of-the-art deep networks (convolutional neural network (CNN) and long short-term memory (LSTM)) and shallow networks (support vector machine (SVM) and artificial neural network (ANN)).

AB - This paper introduces an unsupervised deep Bayesian network, built upon normalizing flow and deep Bayesian network principles, to precisely evaluate the transient security condition of a power system. The proposed approach can capture locational and temporal features using an imbalanced dataset, is noise-model-free, and can handle unlabeled data. It can learn interdependencies between different signals and understand high-dimensional signals in power systems. To validate its effectiveness, the proposed method is studied using the New England power system and shows accuracy and reliability in comparison with state-of-the-art deep networks (convolutional neural network (CNN) and long short-term memory (LSTM)) and shallow networks (support vector machine (SVM) and artificial neural network (ANN)).

KW - Bayesian network

KW - imbalanced dataset

KW - noise-model free

KW - normalizing flow

KW - transient security assessment

KW - unsupervised deep learning

UR - https://www.scopus.com/pages/publications/85185770671

U2 - 10.1109/ETFG55873.2023.10407830

DO - 10.1109/ETFG55873.2023.10407830

M3 - Conference article published in proceeding or book

AN - SCOPUS:85185770671

T3 - 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

BT - 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

Y2 - 3 December 2023 through 6 December 2023

ER -

Afrasiabi S, Allahmoradi S, Liang X, Afrasiabi M, Aghaei J, Chung CY. Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network. In 2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023). doi: 10.1109/ETFG55873.2023.10407830

Power System Transient Security Assessment using Unsupervised Probabilistic Deep Bayesian Neural Network

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this